CN115345392A - Abnormal situation studying and judging and key index screening method for power distribution network - Google Patents
Abnormal situation studying and judging and key index screening method for power distribution network Download PDFInfo
- Publication number
- CN115345392A CN115345392A CN202110516920.9A CN202110516920A CN115345392A CN 115345392 A CN115345392 A CN 115345392A CN 202110516920 A CN202110516920 A CN 202110516920A CN 115345392 A CN115345392 A CN 115345392A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- power distribution
- index
- health degree
- indexes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012216 screening Methods 0.000 title claims abstract description 25
- 230000036541 health Effects 0.000 claims abstract description 193
- 238000011156 evaluation Methods 0.000 claims abstract description 67
- 230000009467 reduction Effects 0.000 claims abstract description 32
- 238000010801 machine learning Methods 0.000 claims abstract description 21
- 238000005516 engineering process Methods 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 230000007547 defect Effects 0.000 claims description 91
- 238000012797 qualification Methods 0.000 claims description 22
- 238000012423 maintenance Methods 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 17
- 230000007613 environmental effect Effects 0.000 claims description 16
- 238000011002 quantification Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 6
- 230000032683 aging Effects 0.000 claims description 4
- 238000011084 recovery Methods 0.000 claims description 4
- 238000004146 energy storage Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004870 electrical engineering Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 30
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 238000013210 evaluation model Methods 0.000 description 4
- 230000003862 health status Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 206010033799 Paralysis Diseases 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/904—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for studying and judging abnormal situation of a power distribution network and screening key indexes, which relates to the technical field of electrical engineering, and adopts the technical scheme that key evaluation indexes of the health degree of the power distribution network are screened as key characteristic quantities; normalizing the key characteristic quantity data acquired in the step S1; building a power distribution network health degree evaluation index system: determining the evaluation index weight of the health degree of the power distribution network by adopting an entropy weight method; and (5) calculating the health degree grade of the power distribution network in a weighting manner to make a health degree portrait. Through distribution network health degree portrait monitoring, when health degree worsens, make unusual early warning to the distribution network. The beneficial effects of the invention are: the method is characterized in that dimensionality reduction processing is carried out on the evaluation index of the health degree of the power distribution network based on a machine learning data dimensionality reduction technology, the key index which can most effectively represent three dimensionalities of safety, reliability and economy of the power distribution network and healthy operation is screened out, meanwhile, an entropy weight method is utilized to endow the key index, a comprehensive and accurate evaluation index system of the health degree of the power distribution network is formed, and then the health degree of the power distribution network is effectively evaluated.
Description
Technical Field
The invention relates to the technical field of electrical engineering, in particular to a method for studying and judging abnormal situations of a power distribution network and screening key indexes.
Background
As the last link of the power system, the normal operation of the distribution network is related to the requirements of users on stability, safety, high quality, economy and the like in the aspect of power utilization. In the operation process of the power distribution network, the power distribution network can enter an abnormal state due to internal or external interference, so that the safe operation of the whole power system is influenced. Therefore, the estimation and judgment of the abnormal state of the power distribution network can improve the power supply quality and reliability of the whole power distribution network, and have important scientific and economic values.
The traditional anomaly detection is based on individual detection, and the line information with certain delay is matched with a database through an SCADA/EMS system and an offline database, so that the anomaly is found. The method has the defects of high delay, low sampling accuracy, dispersed detection modes and the like, and mass data emerge in the power distribution network along with the development of the Internet of things technology and the measuring device, so that a new opportunity is provided for detecting the abnormal state of the power distribution network.
In recent years, many studies on the health of power distribution networks have been conducted at home and abroad. The distribution network is a real-time dynamic system, so that the real-time running state of the distribution network with large quantity, wide range, complexity and changeability can be visually described by using the health degree, the health condition of the existing distribution network is reflected, and whether the running of the distribution network is in a normal state or not can be judged. In addition, when massive data are mined and counted, the classical statistical theorem is no longer applicable, and a high-dimensional random matrix is used for replacing the classical statistical theorem. Based on a high-dimensional random matrix, the abnormal state of the power distribution network can be identified and the time-space characteristics of the power distribution network can be mined by taking time series analysis and a random matrix theory as a cornerstone and analyzing multi-source data of the power distribution network from the characteristics of measured big data.
Disclosure of Invention
Aiming at the technical problems, the invention aims to provide a method for studying and judging the abnormal situation of the power distribution network and screening key indexes, which is used for preliminarily judging the abnormal development situation of the power distribution network by excavating the key indexes of the power distribution network, depicting the real-time portrait of the health degree of the power distribution network and further judging the abnormal development situation of the power distribution network; the abnormal situation studying and judging model of the power distribution network is established based on the key indexes, the abnormal state of the power distribution network can be predicted in advance, risk prevention and control measures can be taken in time, and the method is particularly important for guaranteeing the power supply safety and reliability of the power distribution network.
The technical proposal is that the method comprises the steps of,
s1, screening key evaluation indexes of the health degree of the power distribution network as key characteristic quantities: the method is characterized in that the dimension reduction is carried out on the health degree evaluation indexes of the power distribution network based on a machine learning data dimension reduction technology, and the health degree evaluation result of the power distribution network is obtained by using a small number of key basic indexes;
s2, normalizing the key characteristic quantity data acquired in the S1;
s3, establishing a power distribution network health degree evaluation index system: determining the weight of the evaluation index of the health degree of the power distribution network by adopting an entropy weight method;
and S4, weighting and calculating the health degree grade of the power distribution network to make a health degree portrait. Through distribution network health degree portrait monitoring, when health degree worsens, make unusual early warning to the distribution network.
Preferably, the S1 is used for screening key evaluation indexes of the health degree of the power distribution network, specifically, a first-level index and a second-level index are defined, the evaluation of the health degree of the power distribution network by the first-level index comprises at least three dimensions, and the three dimensions are safe, reliable and economical respectively; and reducing the dimension of the evaluation index of the health degree of the power distribution network by adopting a machine learning data dimension reduction technology to the secondary index to obtain a key index of the health degree of the power distribution network.
Preferably, the key feature quantity data in S2 is normalized, specifically, the quantitative index and the qualitative index are processed, and the original data is normalized to [0,1] for calculating the target value.
Preferably, the S3 establishes a power distribution network health degree evaluation index system, specifically, calculates each index weight by using an entropy weight method, and includes the following steps:
calculating entropy and redundancy of the index:
in the formula: e.g. of a cylinder i And d i Are respectively an index x i Entropy and redundancy of, wherein
Y ij Is the index x of the jth sample i Normalized values, n being the total number of samples; the redundancy measures the difference between the indexes, the larger the difference is, the more important the index is, and the weight value of the ith index is calculated as follows:
in the formula, d i Is an index x i The redundancy of the power distribution network is calculated, k represents the total number of indexes, and the comprehensive health degree score of the power distribution network per day can be obtained by further weighting according to the indexes, so that an overall evaluation score is obtained.
Preferably, the step 4 is to calculate the health degree grade of the power distribution network, make a health degree figure and perform early warning on the abnormity of the power distribution network, specifically, perform weighted calculation on the excavated key indexes representing the health degree of the power distribution network to obtain the finally evaluated health degree of the power distribution network. When the health state of the distribution network is a general defect, a serious defect or a critical defect, the distribution network performance is partially degraded or seriously degraded, and the distribution network has an abnormal development situation.
Preferably, the machine learning index dimension reduction technology comprises the following specific steps:
step one, researching and combing 25 factors and evaluation indexes which influence the health state of a power distribution network, wherein the 25 indexes comprise current harmonic distortion rate, reactive compensation capacity ratio, load transfer rate, average peak-valley difference, rapid switching rate, voltage qualification rate, frequency qualification rate, power factor qualification rate, power supply radius qualification rate, loss qualification rate, comprehensive line loss rate, energy storage capacity ratio, wind power level, lightning level, ice and snow disaster level, line average load rate, fault recovery time, failure conformity rate, power distribution network capacity ratio, peak load duration, three-phase unbalance rate, line section qualification rate, power supply load stability rate, power supply fault self-healing rate and node voltage stability;
step two, clustering and dimensionality reduction of basic indexes:
normalizing 25 basic indexes, clustering by using a DBSCAN clustering method, randomly rejecting one index, clustering the remaining 24 indexes, and if the clustering error of two times is less than or equal to 0.5, indicating that the rejected index does not influence the overall evaluation, is a redundant index and should be discarded; otherwise, if the clustering error is larger than 0.5, the index is reserved; and by analogy, the dimension reduction of the basic indexes is completed until no redundant indexes exist.
Preferably, the index is normalized to [0,1], specifically,
the quantitative index quantification method uses an extreme value method; the 25 indexes all belong to positive indexes, the normalized numerical value is consistent with the variation trend of the original value, and the index numerical value normalization conversion formula is as follows:
the larger the numerical values of indexes such as line loss rate and the like are, the more negative the influence on the health degree of the power distribution network is, the indexes belong to inverse indexes, the normalized numerical value is reduced along with the increase of the original value, and the conversion formula of the numerical value normalization of the inverse indexes is as follows:
in the formula: x is the current value; y is a normalized value; maxValue is the maximum value in the attribute range; minValue is the minimum value in the attribute range;
the qualitative index is static evaluation of the power distribution network, and the quantitative processing can be continued only after the qualitative evaluation is quantified; according to the difference of the index value change types, the qualitative index is divided into a continuous index and a discrete index;
the value range of the value of the continuous index is in a fixed numerical range, and a quantized value is solved according to a linear relation; the discrete index is to define a score range, for example, when a qualitative index is described in a mode of using "high, middle, low and low", and the quantitative index is used for realizing the quantification of the result by using "l, 2, 3,4 and 5" according to the sequence among the qualitative indexes; these quantified results "1, 2, 3,4, 5" may take "0.1, 0.3, 0.5, 0.7, 0.9" as their normalized values, respectively.
Preferably, the health status is classified into health, sub-health, general defect, serious defect, and critical defect according to the value range of the health status, and each health status is represented by green, blue, yellow, orange, and red images. Through monitoring the health degree portrait, when the health degree becomes poor, abnormal early warning is made to the distribution network.
Preferably, the health image represents a meaning including a health image, a sub-health image, a general defect image, a serious defect image, and a critical defect image.
Health portrait: the power distribution network can continue to execute the specified functions in a specified time and under specified conditions without obstacles, the power supply is safe and reliable, the 3-dimensional economical performance reaches the standard, the corresponding key characteristic quantity margin is sufficient, and the resistance risk and the environmental adaptability are strong (complete functions and excellent performance). As long as the daily operation and maintenance strategy is normally executed, the defects and risks are timely found and solved.
Sub-health portrait: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, the 3-dimensional performances of power supply safety, reliability, economy and the like reach the standard, but part of key characteristic quantities are close to the standard limit value, and the resistance risk and the environmental adaptability are reduced (complete functions and reduced performance). The defects and risks need to be paid attention to, but the defects and risks can be found and solved in time only by normally executing a daily operation and maintenance strategy.
General defect image: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, but the performance of 3 dimensions such as power supply safety, reliability and economy is partially degraded, the corresponding characteristic quantity indexes are out of limit, but the comprehensive influence degree is small, and the resistance risk and the environmental adaptability have slight defects (complete functions and slight defects of performance). The defects and risks of the power distribution network need to be considered, the risks are avoided by strictly executing inspection, overhaul and test processes, and the health level can be improved by taking corresponding measures for improving the safety, reliability and economy of the power distribution network.
Serious defect portrait: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, but the performances of power supply safety, reliability and the like are partially seriously degraded, the corresponding characteristic quantity indexes are out of limit, the comprehensive influence degree is large, and the resistance risk and the environmental adaptability have obvious defects (complete functions and obvious performance defects). And warning the power distribution network staff to adopt corresponding measures for improving the safety, reliability and economy of the power distribution network to improve the health level, otherwise, the power distribution network is easy to be in an emergency defect state.
Emergency defect portrayal: the power distribution network cannot normally execute the specified functions, and the performance of dimensions such as power supply safety, reliability and the like is seriously degraded, so that the consequences are serious. The power distribution network staff needs to pay attention to the power distribution network, measures are increased in a targeted mode, and otherwise the power distribution network faces paralysis.
Preferably, when the health degree is deteriorated, an abnormal early warning is given to the power distribution network, specifically,
when the health degree images continuously keep a common defect state for 24 hours, an abnormal early warning is given to the power distribution network, potential faults exist in the performance of the power distribution network, maintenance needs to be arranged, and line faults are mainly eliminated;
when the health degree portrait is continuous for 12 hours and keeps a serious defect state, abnormal early warning is given to the power distribution network, the power distribution network is prompted to resist risks and obviously degrade the environmental adaptability, potential faults exist, maintenance needs to be arranged, and faults of lines and power failure units are mainly investigated;
when the health degree portrait becomes a critical defect state, an abnormal early warning is immediately made for the power distribution network, the performance of the power distribution network is prompted to have serious defects, faults are likely to occur, and immediate arrangement and maintenance are required, wherein the faults include aging of lines and power distribution equipment, unreasonable structure of the power distribution network and the like.
Preferably, the key index is an index of the power distribution network.
The technical scheme provided by the embodiment of the invention has the following beneficial effects: (1) The method is used for carrying out dimensionality reduction treatment on the evaluation index of the health degree of the power distribution network based on the machine learning data dimensionality reduction technology, screening out the key index which can effectively represent the three dimensionalities of safety, reliability and economy of the power distribution network and healthy operation, and meanwhile, weighting the key index by using an entropy weight method (objective weighting method) to form a comprehensive and accurate evaluation index system of the health degree of the power distribution network, so that the health degree of the power distribution network is effectively evaluated.
(2) The health degree portrait of the power distribution network established by the invention clearly and intuitively shows the change trend of the health degree of the power distribution network along with time, reflects the health state of the whole power distribution network from two dimensions of time and space, can monitor the health degree level of the power distribution network in real time through the portrait and makes preliminary early warning on the abnormal situation of the power distribution network.
(3) The method is based on the high-dimensional random matrix, starts from the characteristics of measured big data, takes time sequence analysis and a random matrix theory as a cornerstone, identifies the abnormal state of the power distribution network and excavates the time-space characteristics of the power distribution network by analyzing the multi-source data of the power distribution network, and has important significance for guaranteeing the power supply safety and reliability of the power distribution network.
Drawings
Fig. 1 is a power distribution network health degree evaluation index system according to an embodiment of the present invention.
Fig. 2 is a block diagram of a power distribution network health degree calculation process according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a health level and a corresponding health status of a power distribution network according to an embodiment of the present invention.
Fig. 4 is a distribution network health degree image according to an embodiment of the invention.
Fig. 5 is a result of predicting a value of a spectral density function of a power distribution network according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. Of course, the specific embodiments described herein are merely illustrative of the invention and are not intended to be limiting.
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example 1
Referring to fig. 1 to 5, the present invention provides a method for studying and judging abnormal situation of a distribution network and screening key indexes, comprising the steps of,
s1, screening key evaluation indexes of the health degree of the power distribution network as key characteristic quantities: the method is characterized in that the dimension reduction is carried out on the health degree evaluation indexes of the power distribution network based on a machine learning data dimension reduction technology, and the health degree evaluation result of the power distribution network is obtained by using a small number of key basic indexes;
s2, normalizing the key feature quantity data acquired in the S1;
s3, establishing a power distribution network health degree evaluation index system: determining the weight of the evaluation index of the health degree of the power distribution network by adopting an entropy weight method;
and S4, weighting and calculating the health degree grade of the power distribution network to make a health degree portrait. Through distribution network health degree portrait monitoring, when health degree worsens, make unusual early warning to the distribution network.
S1, screening key evaluation indexes of the health degree of the power distribution network, specifically defining a first-level index and a second-level index, wherein the first-level index for evaluating the health degree of the power distribution network comprises at least three dimensions which are safe, reliable and economical respectively; and reducing the dimension of the evaluation index of the health degree of the power distribution network by adopting a machine learning data dimension reduction technology for the secondary index to obtain a key index of the health degree of the power distribution network.
And S2, normalizing the key characteristic quantity data, specifically, processing a quantitative index and a qualitative index, and normalizing the original data to [0,1] for calculating a target value.
S3, establishing a power distribution network health degree evaluation index system, specifically, calculating each index weight by adopting an entropy weight method, and comprising the following steps:
calculating entropy and redundancy of the index:
in the formula: e.g. of the type i And d i Are respectively an index x i Entropy and redundancy of, wherein
Y ij Is the index x of the jth sample i Normalized values, n being the total number of samples; the redundancy measures the difference between the indexes, the larger the difference is, the more important the index is, and the weight value of the ith index is calculated as follows:
in the formula (d) i Is an index x i The redundancy of the power distribution network is calculated, k represents the total number of indexes, and the comprehensive health degree score of the power distribution network per day can be obtained by further weighting according to the indexes, so that an overall evaluation score is obtained.
And S4, calculating the health degree grade of the power distribution network, making a health degree portrait and giving an abnormal early warning to the power distribution network, specifically, performing weighted calculation on the excavated key indexes representing the health degree of the power distribution network to obtain the finally evaluated health degree of the power distribution network. And determining the health state of the power distribution network according to the value range of the health degree. As shown in the following table:
when the health state of the power distribution network is a general defect, a serious defect or a critical defect, the performance of the power distribution network is partially degraded or seriously degraded, and the abnormal development situation is shown.
The index is normalized to [0,1], specifically,
the quantitative index quantification method uses an extreme value method; the 25 indexes all belong to positive indexes, the normalized numerical value is consistent with the change trend of the original value, and the index numerical value normalization conversion formula is as follows:
the larger the numerical values of indexes such as line loss rate and the like are, the more negative the influence on the health degree of the power distribution network is, the indexes belong to inverse indexes, the normalized numerical value is reduced along with the increase of the original value, and the conversion formula of the numerical value normalization of the inverse indexes is as follows:
in the formula: x is a current value; y is a normalized value; maxValue is the maximum value in the attribute range; minValue is the minimum value in the attribute range;
the qualitative index is static evaluation of the power distribution network, and the quantitative processing can be continued only after the qualitative evaluation is quantified; according to the difference of the index value change types, the qualitative index is divided into a continuous index and a discrete index;
the value range of the continuous index is in a fixed numerical range, and a quantized value is calculated according to a linear relation; the discrete index is to define a score range, for example, when a qualitative index is described in a mode of using "high, middle, low and low", and the quantitative index is used for realizing the quantification of the result by using "l, 2, 3,4 and 5" according to the sequence among the qualitative indexes; these quantified results "1, 2, 3,4, 5" may take "0.1, 0.3, 0.5, 0.7, 0.9" as their normalized values, respectively.
The health degree states are divided into health, sub-health, general defect, serious defect and critical defect according to the value range of the health degree, and each health degree state is represented by green, blue, yellow, orange and red pictures. Through monitoring the health degree portrait, when the health degree becomes poor, abnormal early warning is made to the distribution network.
The health image includes health image, sub-health image, general defect image, serious defect image and critical defect image.
Health portrait: the power distribution network can continue to execute the specified functions in a specified time and under specified conditions without obstacles, the power supply is safe and reliable, the 3-dimensional economical performance reaches the standard, the corresponding key characteristic quantity margin is sufficient, and the resistance risk and the environmental adaptability are strong (complete functions and excellent performance). As long as the daily operation and maintenance strategy is normally executed, the defects and risks are timely found and solved.
Sub-health portrait: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, the 3-dimensional performances of power supply safety, reliability, economy and the like reach the standard, but part of key characteristic quantities are close to the standard limit value, and the resistance risk and the environmental adaptability are reduced (complete functions and reduced performance). The defects and risks need to be paid attention to, but the defects and risks can be found and solved in time only by normally executing a daily operation and maintenance strategy.
General defect image: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, but the performance of 3 dimensions such as power supply safety, reliability and economy is partially degraded, the corresponding characteristic quantity indexes are out of limit, but the comprehensive influence degree is small, and the resistance risk and the environmental adaptability have slight defects (complete functions and slight defects of performance). The defects and risks of the power distribution network need to be considered, the risks are avoided by strictly executing inspection, overhaul and test processes, and the health level can be improved by taking corresponding measures for improving the safety, reliability and economy of the power distribution network.
Serious defect portrait: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, but the performances of power supply safety, reliability and the like are partially seriously degraded, the corresponding characteristic quantity indexes are out of limit, the comprehensive influence degree is large, and the resistance risk and the environmental adaptability have obvious defects (complete functions and obvious performance defects). And warning the power distribution network staff to adopt corresponding measures for improving the safety, reliability and economy of the power distribution network to improve the health level, otherwise, the power distribution network is easy to be in an emergency defect state.
Emergency defect portrayal: the power distribution network cannot normally execute the specified functions, and the performance of dimensions such as power supply safety, reliability and the like is seriously degraded, so that the consequences are serious. The power distribution network staff needs to pay attention to the power distribution network, measures are increased in a targeted mode, and otherwise the power distribution network faces paralysis.
When the health degree is deteriorated, abnormal early warning is given to the power distribution network, specifically,
when the health degree images continuously keep a common defect state for 24 hours, an abnormal early warning is given to the power distribution network, potential faults exist in the performance of the power distribution network, maintenance needs to be arranged, and line faults are mainly eliminated;
when the health degree images continuously keep a serious defect state for 12 hours, performing abnormal early warning on the power distribution network, prompting that the resistance risk and the environmental adaptability of the power distribution network are obviously degraded, and having potential faults, needing to arrange maintenance and mainly troubleshooting faults of lines and power failure units;
when the health degree portrait becomes a critical defect state, an abnormal early warning is immediately made for the power distribution network, the performance of the power distribution network is prompted to have serious defects, faults are likely to occur, and immediate arrangement and maintenance are required, wherein the faults include aging of lines and power distribution equipment, unreasonable structure of the power distribution network and the like.
Example 2
Comprises the steps of (a) preparing a mixture of,
s1, screening key evaluation indexes of the health degree of the power distribution network as key characteristic quantities: the method is characterized in that the dimension reduction is carried out on the health degree evaluation indexes of the power distribution network based on a machine learning data dimension reduction technology, and the health degree evaluation result of the power distribution network is obtained by using a small number of key basic indexes;
defining a first-level index and a second-level index, wherein the first-level index comprises at least three dimensions for evaluating the health degree of the power distribution network, and the three dimensions are safe, reliable and economical respectively; and reducing the dimension of the evaluation index of the health degree of the power distribution network by adopting a machine learning data dimension reduction technology for the secondary index to obtain a key index of the health degree of the power distribution network.
S2, normalizing the key feature quantity data acquired in the S1;
and processing the quantitative index and the qualitative index, and normalizing the original data to [0,1] for calculating a target value.
S3, establishing a power distribution network health degree evaluation index system: determining the weight of the evaluation index of the health degree of the power distribution network by adopting an entropy weight method;
and calculating each index weight by adopting an entropy weight method, and the method comprises the following steps:
calculating entropy and redundancy of the index:
in the formula: e.g. of the type i And d i Are respectively an index x i Entropy and redundancy of, wherein
Y ij Is the index x of the jth sample i Normalized value, n is the total number of samples; the redundancy measures the difference between the indexes, the larger the difference is, the more important the index is, and the weight value of the ith index is calculated as follows:
in the formula (d) i Is an index x i The redundancy of the power distribution network is obtained, k represents the total number of indexes, and the health degree comprehensive score of the power distribution network per day can be obtained by further weighting according to the indexes, so that an overall evaluation score is obtained.
And S4, weighting and calculating the health degree grade of the power distribution network to make a health degree portrait. Through distribution network health degree portrait monitoring, when health degree worsens, make unusual early warning to the distribution network.
And performing weighted calculation on the excavated key indexes representing the health degree of the power distribution network to obtain the finally evaluated health degree of the power distribution network. And determining the health state of the power distribution network according to the value range of the health degree. As shown in the following table:
when the health state of the power distribution network is a general defect, a serious defect or a critical defect, the performance of the power distribution network is partially degraded or seriously degraded, and the abnormal development situation is shown.
The machine learning index dimension reduction technology comprises the following specific steps:
step one, researching and combing 25 factors and evaluation indexes which influence the health state of a power distribution network, wherein the 25 indexes comprise current harmonic distortion rate, reactive compensation capacity ratio, load transfer rate, average peak-valley difference, rapid switching rate, voltage qualification rate, frequency qualification rate, power factor qualification rate, power supply radius qualification rate, loss qualification rate, comprehensive line loss rate, energy storage capacity ratio, wind power level, lightning level, ice and snow disaster level, line average load rate, fault recovery time, failure conformity rate, power distribution network capacity ratio, peak load duration, three-phase unbalance rate, line section qualification rate, power supply load stability rate, power supply fault self-healing rate and node voltage stability;
step two, clustering and dimensionality reduction of basic indexes:
normalizing 25 basic indexes, clustering by using a DBSCAN clustering method, randomly rejecting one index, clustering the remaining 24 indexes, and if the clustering error of two times is less than or equal to 0.5, indicating that the rejected index does not influence the overall evaluation, is a redundant index and should be discarded; otherwise, if the clustering error is larger than 0.5, the index is reserved; and repeating the steps until no redundant indexes exist, and finishing the dimension reduction of the basic indexes.
The index is normalized to [0,1], specifically,
the quantitative index quantification method uses an extreme value method; the 25 indexes all belong to positive indexes, the variation trend of the normalized numerical value is consistent with that of the original value, and the index numerical value normalization conversion formula is as follows:
the larger the numerical values of indexes such as line loss rate and the like are, the more negative the influence on the health degree of the power distribution network is, the indexes belong to inverse indexes, the normalized numerical value is reduced along with the increase of the original value, and the conversion formula of the numerical value normalization of the inverse indexes is as follows:
in the formula: x is the current value; y is a normalized value; maxValue is the maximum value in the attribute range; minValue is the minimum value in the attribute range;
the qualitative index is static evaluation of the power distribution network, and the quantitative processing can be continued only after the qualitative evaluation is quantified; according to the difference of the index value change types, the qualitative index is divided into a continuous index and a discrete index;
the value range of the continuous index is in a fixed numerical range, and a quantized value is calculated according to a linear relation; the discrete index is to customize a score range, for example, when the mode of 'high, medium, low and low' is used, a qualitative index is described, and the 'l, 2, 3,4 and 5' are used according to the sequence among the indexes to realize the quantification of the result; the results "1, 2, 3,4, 5" after these quantifications may take "0.1, 0.3, 0.5, 0.7, 0.9" as their normalized values, respectively.
The health degree states are divided into health, sub-health, general defect, serious defect and critical defect according to the value range of the health degree, and each health degree state is represented by green, blue, yellow, orange and red pictures. Through monitoring the health degree portrait, when the health degree becomes poor, abnormal early warning is made to the distribution network.
The health image includes health image, sub-health image, general defect image, serious defect image and critical defect image.
Health portrait: the power distribution network can continue to execute the specified functions in a specified time and under specified conditions without obstacles, the power supply is safe and reliable, the 3-dimensional economical performance reaches the standard, the corresponding key characteristic quantity margin is sufficient, and the resistance risk and the environmental adaptability are strong (complete functions and excellent performance). As long as the daily operation and maintenance strategy is normally executed, the defects and risks are timely found and solved.
Sub-health portrait: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, the 3-dimensional performances of power supply safety, reliability, economy and the like reach the standard, but part of key characteristic quantities are close to the standard limit value, and the resistance risk and the environmental adaptability are reduced (complete functions and reduced performance). The defects and risks need to be paid attention to, but the defects and risks can be found and solved in time only by normally executing a daily operation and maintenance strategy.
General defect image: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, but the performance of 3 dimensions such as power supply safety, reliability and economy is partially degraded, the corresponding characteristic quantity indexes are out of limit, but the comprehensive influence degree is small, and the resistance risk and the environmental adaptability have slight defects (complete functions and slight defects of performance). The defects and risks of the power distribution network need to be considered, the risks are avoided by strictly executing inspection, overhaul and test processes, and the health level can be improved by taking corresponding measures for improving the safety, reliability and economy of the power distribution network.
Serious defect portrayal: the power distribution network can normally execute the specified functions within the specified time and under the specified conditions, but the performances of power supply safety, reliability and the like are partially seriously degraded, the corresponding characteristic quantity indexes are out of limit, the comprehensive influence degree is large, and the resistance risk and the environmental adaptability have obvious defects (complete functions and obvious performance defects). And warning the power distribution network staff to adopt corresponding measures for improving the safety, reliability and economy of the power distribution network to improve the health level, otherwise, the power distribution network is easy to be in an emergency defect state.
Emergency defect portrayal: the power distribution network cannot normally execute the specified functions, and the performance of dimensions such as power supply safety, reliability and the like is seriously degraded, so that the consequences are serious. The power distribution network staff needs to pay attention to the power distribution network, measures are increased in a targeted mode, and otherwise the power distribution network faces paralysis.
When the health degree is deteriorated, abnormal early warning is given to the power distribution network, specifically,
when the health degree images continuously keep a common defect state for 24 hours, an abnormal early warning is given to the power distribution network, potential faults exist in the performance of the power distribution network, maintenance needs to be arranged, and line faults are mainly eliminated;
when the health degree images continuously keep a serious defect state for 12 hours, performing abnormal early warning on the power distribution network, prompting that the resistance risk and the environmental adaptability of the power distribution network are obviously degraded, and having potential faults, needing to arrange maintenance and mainly troubleshooting faults of lines and power failure units;
when the health degree portrait becomes a critical defect state, an abnormal early warning is immediately made for the power distribution network, the performance of the power distribution network is prompted to have serious defects, faults are likely to occur, and immediate arrangement and maintenance are required, wherein the faults include aging of lines and power distribution equipment, unreasonable structure of the power distribution network and the like.
Example 3
The invention provides a method for studying and judging abnormal situation of a power distribution network and screening key indexes, which comprises the following steps:
(1) Screening key evaluation indexes of the health degree of the power distribution network: the health degree of the power distribution network is evaluated by taking 3 safe, reliable and economical dimensions as primary indexes, and the health degree evaluation indexes of the power distribution network are subjected to dimension reduction by adopting a machine learning data dimension reduction technology for secondary indexes, so that the health degree evaluation result of the power distribution network is obtained by using a small number of key basic indexes. The machine learning index dimension reduction technology comprises the following specific steps:
step 1: simulation sample data set established based on power distribution network health degree evaluation model
In order to apply a machine learning feature selection algorithm to perform index dimension reduction, firstly, simulation sample data required by machine learning is constructed. According to the project, target value operation is carried out on each group of index data based on the established power distribution network health degree evaluation model, and the final evaluation result is used as a label of the group of data. And randomly generating 300 data samples of the index data in the risk assignment range, wherein each sample comprises 36-dimensional index data and one label data. Each group of data consists of the normalized values of all secondary indexes for evaluating the health degree of the power distribution network and the corresponding labels obtained by calculating the index values. The 300 pieces of data should include equivalent data of five labels which can respectively judge that the power distribution network is healthy, sub-healthy, general defect, serious defect and critical defect. Namely, 60 secondary index values in the data set are subjected to comprehensive index operation to obtain a health degree evaluation result of the power distribution network, namely 'health'; after 60 secondary index values are subjected to comprehensive index operation, the health degree evaluation result of the power distribution network is sub-health; the health degree evaluation result of the power distribution network obtained by carrying out comprehensive index operation on 60 secondary index values is a 'general defect'; after 60 secondary index values are subjected to comprehensive index operation, the health degree evaluation result of the power distribution network is a 'serious defect'; and after 60 secondary index values are subjected to comprehensive index operation, the health degree evaluation result of the power distribution network is the critical defect. Therefore, all possible classification conditions obtained by evaluating the index values are contained in the data set, and accurate classification and feature selection of machine learning are facilitated.
Step 2: establishment of basic index dimension reduction and power distribution network health degree evaluation model
And (3) sending data such as voltage and line loss into a program for selecting machine learning characteristics, and obtaining an importance ranking graph of each basic index such as voltage qualification rate and comprehensive line loss rate and an importance value of each basic index in classification decision through a decision tree classification training model. And performing machine learning classification training and feature selection simulation experiments under a Python 3.7 software platform. And installing a machine learning toolkit sklern based on Python language, selecting a decision tree model in the toolkit for classification training and performing feature selection. And (3) performing classification prediction by using a classification method based on a Decision Tree, wherein a label can select a precision Tree Classifier function, and the precision Tree Classifier can be used for multi-classification. Calculating the importance of each basic index such as voltage qualification rate, comprehensive line loss rate and the like in classification decision by using a dtre. Under the same scene, when the evaluation model is used for evaluating the health degree of the power distribution network, only the numerical values of the basic indexes after dimension reduction are collected.
(2) Index system for evaluating health degree of power distribution network
And (3) reducing the dimension of the index system to obtain 6 key indexes, namely voltage qualification rate, power factor qualification rate, fault recovery time, comprehensive line loss rate, line average load rate and load transfer rate. The 6 key indexes are mapped to 3 safe, reliable and economical evaluation dimensions to form a distribution network health degree evaluation index system after dimension reduction, as shown in figure 1. The weights of the indexes are determined based on the entropy weight method, and are shown in the following table:
(3) Calculating the health degree grade of the power distribution network
The distribution network health degree calculation process is shown in fig. 2, firstly, key indexes representing the distribution network health degree are input, weighting calculation is carried out, the finally calculated distribution network health degree can be obtained, and the health state of the distribution network can be determined according to the value range of the health degree. As shown in fig. 3, five colors respectively represent five health states of the distribution network, for example, green represents that the health level is [4,5], i.e. the health state; blue represents a fitness level at [3,4], i.e., sub-health, and so on.
(4) Making a health sketch
Taking a certain power distribution network in east of Shandong as an example, a health degree image of the east-first change, the east-second change, the east-third change, the east-fourth change, the east-fifth change, the east-sixth change and the east-net change in 11 and 27 days of 2020 is made, as shown in FIG. 4. In the figure, the abscissa represents time in hours, and the ordinate represents the substation. It can be seen from the figure that on the day of 11 months and 27 days, the health states of other substations except for the east-fourth change are kept healthy or sub-healthy, and general defects occur only at certain moments. The health degree of the east-IV change is always kept at a common defect, and the early warning function is played for the abnormal situation of the east-IV change.
And analyzing the evaluation indexes of the health degree of the east four change, and finding that the safety, reliability and economic score are respectively 2.54, 3.78 and 2.92, wherein the comprehensive line loss rate score of the load transfer rate of the safety index and the economic index is lower than 3.0. Through field inspection, the line loss rate is higher than 15% when a certain line switch is disconnected by mistake, and the load transfer rate is improved by 3.8% by reclosing the switch; by increasing the capacity of the reactive compensator, the line loss is reduced by 1.2%.
In addition, the abnormal time of the abnormal power distribution network is verified, and the actual abnormal time of the power distribution network is found to be in accordance with the expected abnormal early warning time, which shows that the abnormal state of the power distribution network can be mined and the abnormal early warning can be given to the power distribution network.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A method for studying and judging abnormal situation of a power distribution network and screening key indexes is characterized by comprising the following steps,
s1, screening key evaluation indexes of the health degree of the power distribution network as key characteristic quantities: performing dimension reduction on the evaluation index of the health degree of the power distribution network based on a machine learning data dimension reduction technology;
s2, normalizing the key feature quantity data acquired in the S1;
s3, establishing a power distribution network health degree evaluation index system: determining the weight of the evaluation index of the health degree of the power distribution network by adopting an entropy weight method;
and S4, weighting and calculating the health degree grade of the power distribution network to make a health degree portrait. Through distribution network health degree portrait monitoring, when health degree worsens, make unusual early warning to the distribution network.
2. The method for studying and judging the abnormal situation of the power distribution network and screening the key indexes according to claim 1, wherein S1 is used for screening key evaluation indexes of the health degree of the power distribution network, and specifically, a primary index and a secondary index are defined, and the evaluation of the health degree of the power distribution network by the primary index comprises at least three dimensions; and reducing the dimension of the evaluation index of the health degree of the power distribution network by adopting a machine learning data dimension reduction technology to the secondary index to obtain a key index of the health degree of the power distribution network.
3. The method for studying and judging the abnormal situation of the power distribution network and screening the key indexes according to claim 1, wherein the key characteristic quantity data in the step S2 is normalized, specifically, quantitative indexes and qualitative indexes are processed, and original data are normalized to [0,1] for calculating target values.
4. The method for studying and judging abnormal situation of the power distribution network and screening key indexes according to claim 1, wherein the S3 is used for establishing a power distribution network health degree evaluation index system, specifically, an entropy weight method is used for calculating each index weight, and the method comprises the following steps:
calculating entropy and redundancy of the index:
in the formula: e.g. of the type i And d i Are respectively an index x i Entropy and redundancy of, wherein
Y ij Is the index x of the jth sample i Normalized values, n being the total number of samples; the redundancy measures the difference between the indexes, the larger the difference is, the more important the index is, and the weight value of the ith index is calculated as follows:
in the formula (d) i Is an index x i The redundancy of the power distribution network is obtained, k represents the total number of indexes, and the health degree comprehensive score of the power distribution network per day can be obtained by further weighting according to the indexes, so that an overall evaluation score is obtained.
5. The method for studying and judging abnormal situation and screening key indexes of the power distribution network according to claim 2, wherein S4 is used for calculating the health degree grade of the power distribution network, making a health degree figure and giving an abnormal early warning to the power distribution network, and specifically, weighting calculation is performed on the excavated key indexes representing the health degree of the power distribution network to obtain the finally evaluated health degree of the power distribution network.
6. The method for studying and judging abnormal situation and screening key indexes of the power distribution network according to claim 2, wherein the specific steps of the machine learning index dimension reduction technology are as follows:
step one, researching and combing 25 factors and evaluation indexes which influence the health state of a power distribution network, wherein the 25 indexes comprise current harmonic distortion rate, reactive compensation capacity ratio, load transfer rate, average peak-valley difference, rapid switching rate, voltage qualification rate, frequency qualification rate, power factor qualification rate, power supply radius qualification rate, loss qualification rate, comprehensive line loss rate, energy storage capacity ratio, wind power level, lightning level, ice and snow disaster level, line average load rate, fault recovery time, failure conformity rate, power distribution network capacity ratio, peak load duration, three-phase unbalance rate, line section qualification rate, power supply load stability rate, power supply fault self-healing rate and node voltage stability;
step two, clustering and dimensionality reduction of basic indexes:
after 25 basic indexes are normalized, clustering is carried out by using a DBSCAN clustering method, one index is randomly removed, the remaining 24 indexes are clustered, if the clustering error of two times is less than or equal to 0.5, the removed index does not influence the overall evaluation, is a redundant index and should be discarded; otherwise, if the clustering error is larger than 0.5, the index is reserved; and repeating the steps until no redundant indexes exist, and finishing the dimension reduction of the basic indexes.
7. The method for studying and judging the abnormal situation of the power distribution network and screening the key indexes according to claim 6, wherein the indexes are normalized to [0,1], specifically,
the quantitative index quantification method uses an extreme value method; the 25 indexes all belong to positive indexes, and the index value normalization conversion formula is as follows:
the larger the numerical values of indexes such as line loss rate and the like are, the more negative the influence on the health degree of the power distribution network is, the indexes belong to inverse indexes, and the numerical value normalization conversion formula of the inverse indexes is as follows:
in the formula: x is the current value; y is a normalized value; maxValue is the maximum value in the attribute range; minValue is the minimum value in the attribute range;
according to the difference of the index value change types, the qualitative index is divided into a continuous index and a discrete index;
the value range of the continuous index is in a fixed numerical range, and a quantized value is calculated according to a linear relation; the discrete index is to customize a score range, for example, when the mode of 'high, medium, low and low' is used, a qualitative index is described, and the 'l, 2, 3,4 and 5' are used according to the sequence among the indexes to realize the quantification of the result; the results "1, 2, 3,4, 5" after quantization adopt "0.1, 0.3, 0.5, 0.7, 0.9" as their normalized values, respectively.
8. The method for studying and judging abnormal situation and screening key indexes of the power distribution network according to claim 5, wherein the health degree states are classified into health, sub-health, general defects, serious defects and critical defects according to the value range of the health degree, and each health degree state is represented by green, blue, yellow, orange and red pictures respectively. Through monitoring the health degree portrait, when the health degree becomes poor, abnormal early warning is made to the distribution network.
9. The method for studying and judging the abnormal situation of the power distribution network and screening the key indexes according to claim 8, wherein when the health degree is deteriorated, an abnormal early warning is given to the power distribution network, specifically,
when the health degree images continuously keep a common defect state for 24 hours, an abnormal early warning is given to the power distribution network, potential faults exist in the performance of the power distribution network, maintenance needs to be arranged, and line faults are mainly eliminated;
when the health degree portrait is continuous for 12 hours and keeps a serious defect state, abnormal early warning is given to the power distribution network, the power distribution network is prompted to resist risks and obviously degrade the environmental adaptability, potential faults exist, maintenance needs to be arranged, and faults of lines and power failure units are mainly investigated;
when the health degree portrait becomes a critical defect state, an abnormal early warning is immediately made for the power distribution network, the performance of the power distribution network is prompted to have serious defects, faults are likely to occur, and immediate arrangement and maintenance are required, wherein the faults include aging of lines and power distribution equipment, unreasonable structure of the power distribution network and the like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110516920.9A CN115345392A (en) | 2021-05-12 | 2021-05-12 | Abnormal situation studying and judging and key index screening method for power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110516920.9A CN115345392A (en) | 2021-05-12 | 2021-05-12 | Abnormal situation studying and judging and key index screening method for power distribution network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115345392A true CN115345392A (en) | 2022-11-15 |
Family
ID=83946696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110516920.9A Pending CN115345392A (en) | 2021-05-12 | 2021-05-12 | Abnormal situation studying and judging and key index screening method for power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345392A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629709A (en) * | 2023-07-21 | 2023-08-22 | 国网山东省电力公司青岛市即墨区供电公司 | Intelligent analysis alarm system of power supply index |
-
2021
- 2021-05-12 CN CN202110516920.9A patent/CN115345392A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629709A (en) * | 2023-07-21 | 2023-08-22 | 国网山东省电力公司青岛市即墨区供电公司 | Intelligent analysis alarm system of power supply index |
| CN116629709B (en) * | 2023-07-21 | 2023-10-20 | 国网山东省电力公司青岛市即墨区供电公司 | Intelligent analysis alarm system of power supply index |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103605881A (en) | Fault tree and analytic hierarchy process based evaluation method of state of power transformer | |
| CN106447205A (en) | Method for evaluating state of distribution automation terminal based on analytic hierarchy process | |
| CN110009208B (en) | Method and device for evaluating health state of pole-mounted switch complete equipment based on hybrid intelligent algorithm | |
| CN110530650B (en) | Method for monitoring performance state of heavy-duty gas turbine based on generalized regression neural network and box diagram analysis | |
| CN109490726A (en) | Electric power transformer insulated state evaluating method based on Clouds theory | |
| CN112668943A (en) | Distribution line health state assessment method and system | |
| CN108304931A (en) | A kind of Condition-based Maintenance of Substation Equipment method for diagnosing faults | |
| CN107633349A (en) | Fault impact factor quantitative analysis method based on high-voltage switch gear | |
| CN110503305B (en) | Transformer performance evaluation method | |
| CN112116276B (en) | Substation operation risk assessment method considering time-varying state of electric main equipment | |
| CN112686536A (en) | Power grid disaster response capability quantitative evaluation method based on fuzzy comprehensive evaluation | |
| McGrail et al. | Data mining techniques to assess the condition of high voltage electrical plant | |
| CN113191585A (en) | Typhoon disaster risk assessment method for power transmission line | |
| CN115345392A (en) | Abnormal situation studying and judging and key index screening method for power distribution network | |
| CN114065495A (en) | Transformer state evaluation method based on reverse cloud combination weight and fuzzy closeness | |
| CN117611010A (en) | Fuzzy comprehensive evaluation method for intelligent power distribution cabinet operation state based on twin model | |
| CN109784777B (en) | Power grid equipment state evaluation method based on time sequence information fragment cloud similarity measurement | |
| Li et al. | Fault prediction of power transformer by association rules and markov | |
| CN111369388A (en) | Method and system for evaluating anti-vulnerability of urban power grid | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| CN115310586A (en) | Method and system for predicting operation situation of active power distribution network information physical system aiming at network attack | |
| CN114595966A (en) | Super-huge type urban power grid toughness assessment method considering different disaster types | |
| CN115693692A (en) | Voltage qualification rate improving method based on power distribution network voltage data analysis | |
| CN113052473A (en) | Power grid risk analysis method based on fault rate and static safety analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |